Deep learning with differential equations

Project Details

Description

Machine learning is developing at an unprecented pace due to a paradigm shift caused by deep neural network models, which have revolutionised the several domains of science. Deep neural networks represents learning as a series of deterministic, complex and discrete transformations. In this Aalto University research project we will propose a groundbreaking new viewpoint on machine learning by developing a novel deep learning paradigm of probabilistic continuous-time deep learning, where interpretable, simple distributions of smooth transformations, or time differentials, encode the learning process as a continuous flow. The novel paradigm draws from solid foundations of physics, statistics and dynamical systems literature. The project will be performed in close collaboration with an international network of world-renowned experts in these fields. The project is headed by a machine learning researcher PhD Markus Heinonen.
Short titleHeinonen Markus AT-palkka
StatusActive
Effective start/end date01/09/202031/08/2025

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
  • Bayesian Inference for Optimal Transport with Stochastic Cost

    Mallasto, A., Heinonen, M. & Kaski, S., 2021, Proceedings of Asian Conference on Machine Learning. p. 1601-1616 16 p. (Proceedings of Machine Learning Research; vol. 157).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Open Access
    File
    6 Downloads (Pure)
  • De-randomizing MCMC dynamics with the diffusion Stein operator

    Shen, Z., Heinonen, M. & Kaski, S., 2021, Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021). 11 p. (Advances in Neural Information Processing Systems).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Open Access
    File
    4 Downloads (Pure)